Accurately obtaining the crop quantity and density is not only crucial for the demand-based input of water and fertilizer in the field but also vital for ensuring the yield and quality of crops. Aerial photography by unmanned aerial vehicles (UAVs) can quickly acquire the distribution image information of crops over a large area. However, the accurate recognition of a single type of dense targets is a huge challenge for most recognition algorithms. Taking banana seedlings as an example in this study, we captured the images of banana plantations by UAVs from high altitudes to explore an efficient recognition method for dense targets. We proposed a strategy of "cut-recognition-stitch" and constructed a counting method based on the improved Faster R-CNN algorithm. First, the images containing highly dense targets were cropped into a large number of image tiles according to different sizes (simulating different flight altitudes), and the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm was adopted to improve the image quality. A banana seedling dataset containing 36 000 image tiles was constructed. Then, the Faster R-CNN network with optimized parameters was used to train the banana seedling recognition model. Finally, the recognition results were reversely stitched together, and a boundary deduplication algorithm was designed to correct the final counting results to reduce the repeated recognition caused by image cropping. The results show that the recognition accuracy of the Faster R-CNN with optimized parameters for banana image datasets of different sizes can reach up to 0.99 at most. The deduplication algorithm can reduce the average counting error for the original aerial images from 1.60% to 0.60%, and the average counting accuracy of banana seedlings reaches 99.4%. The proposed method effectively addresses the challenge of recognizing dense small objects in high-resolution aerial images, providing an efficient and reliable technical solution for intelligent crop density monitoring in precision agriculture.
Musa/growth & development* ; Crops, Agricultural/growth & development* ; Algorithms ; Neural Networks, Computer ; Unmanned Aerial Devices ; Seedlings/growth & development* ; Image Processing, Computer-Assisted/methods* ; Photography ; Agriculture/methods*

Objective: At present, surgeons do not know enough about the mesenteric morphology of the colonic splenic flexure, resulting in many problems in the complete mesenteric resection of cancer around the splenic flexure. In this study, the morphology of the mesentery during the mobilization of the colonic splenic flexure was continuously observed in vivo, and from the embryological point of view, the unique mesenteric morphology of the colonic splenic flexure was reconstructed in three dimensions to help surgeons further understand the mesangial structure of the region. Methods: A total of 9 patients with left colon cancer who underwent laparoscopic radical resection with splenic flexure mobilization by the same group of surgeons in Union Hospital of Fujian Medical University from January 2018 to June 2019 were enrolled. The splenic flexure was mobilized using a "three-way approach" strategy based on a middle-lateral approach. During the process of splenic flexure mobilization, the morphology of the transverse mesocolon and descending mesocolon were observed and reconstructed from the embryological point of view. The lower margin of the pancreas was set as the axis, and 4 pictures for each patient (section 1-section 4) were taken during middle-lateral mobilization. Results: The median operation time of the splenic flexure mobilization procedure was 31 (12-55) minutes, and the median bleeding volume was 5 (2-30) ml. One patient suffered from lower splenic vessel injury during the operation and the bleeding was stopped successfully after hemostasis with an ultrasound scalpel. The transverse mesocolon root was observed in all 9 (100%) patients, locating under pancreas, whose inner side was more obvious and tough, and the structure gradually disappeared in the tail of the pancreatic body, replaced by smooth inter-transitional mesocolon and dorsal lobes of the descending colon. The mesenteric morphology of the splenic flexure was reconstructed by intraoperative observation. The transverse mesocolon was continuous with a fan-shaped descending mesocolon. During the embryonic stage, the medial part (section 1-section 2) of the transverse mesocolon and the descending mesocolon were pulled and folded by the superior mesenteric artery (SMA). Then, the transverse mesocolon root was formed by compression of the pancreas on the folding area of the transverse mesocolon and the descending mesocolon. The lateral side of the transverse mesocolon root (section 3-section 4) was distant from the mechanical traction of the SMA, and the corresponding folding area was not compressed by the tail of the pancreas. The posterior mesangial lobe of the transverse mesocolon and the descending mesocolon were continuous with each other, forming a smooth lobe. This smooth lobe laid flat on the corresponding membrane bed composed of the tail of pancreas, Gerota's fascia and inferior pole of the spleen. Conclusions: From an embryological point of view, this study reconstructs the mesenteric morphology of the splenic flexure and proposes a transverse mesocolon root structure that can be observed consistently intraopertively. Cutting the transverse mesocolon root at the level of Gerota's fascia can ensure the complete resection of the mesentery of the transverse colon.
Colectomy/methods* ; Colon, Transverse/surgery* ; Colonic Neoplasms/surgery* ; Dissection ; Fascia/anatomy & histology* ; Humans ; Laparoscopy ; Mesentery/surgery* ; Mesocolon/surgery* ; Pancreas/surgery* ; Photography ; Spleen/surgery*

OBJECTIVE: To explore the possibility of the Smile Lite MDP (Smile Lite Mobile Dental Photograph) portable dental photography system applying in anterior teeth aesthetic photography, and to provide the chance to simplify aesthetic photography process and facilitate communication among patients, dentists and dental technitians. METHODS: The Smile Lite MDP photography system combined with the smartphone were used to photograph the front occlusal phase photos of anterior teeth. The photographic conditions including the color temperature parameter, the Smile Lite MDP light position and the intensity settings were explored. The best photographic conditions were chosen by blind evaluation within experienced dentists and technicians through the method of the visual analogue scale/score (VAS) evaluation, which went through statistical analysis to figure out the optimum photograghic conditions. Smile Lite MDP photography system was used to photograph the front occlusal phase photos of anterior teeth under the optimum parameter by different magnifications. The width/height ratio of the central incisor and the front width ratio of the upper anterior teeth in those photos were measured and calculated respectively. The accuracy of the anterior teeth photos taken by Smile Lite MDP photography system was analyzed based on the photographs taken by digital single lens reflex (DSLR) camera. RESULTS: The optimum color temperature parameter of Smile Lite MDP portable camera system was 5 000 K, the optimum magnification was 4 times, the best light position was the side lights of Smile Lite MDP, the optimum intensity of lights was 2 grades. Photos taken by the optimum parameters won the highest score during the VAS evaluation and the result of statistical analysis had significant difference compared with other groups (P<0.05). When comparing the photos of the upper anterior teeth taken by the Smile Lite MDP portable photography system using 4 times magnification or by DSLR using the standard parameters, there was no significant difference neither in the width/hieght ratio of the central incisor nor in the front width ratio of the upper anterior teeth (P>0.05). CONCLUSION The Smile Lite MDP portable dental photography system applying in anterior teeth aesthetic analysis photography was capable to show the color and shape of anterior teeth in an accurate way by using the right photography parameters. Therefore, Smile Lite MDP portable dental photography system was considered to be a simple and easy photographic tool in clinical work.
Esthetics ; Esthetics, Dental ; Humans ; Incisor ; Photography ; Smiling

PURPOSE: To report a case of non-glaucomatous retinal nerve fiber layer (RNFL) defect associated with paravascular inner retinal defect (PIRD) in a patient with idiopathic epiretinal membrane (ERM).CASE SUMMARY: A 70-year-old male who was diagnosed with ERM in his right eye and pseudoexfoliative glaucoma in his left eye visited our clinic. His intraocular pressure was 14 mmHg in both eyes while using topical hypotensive medications in both eyes. His right eye showed no glaucomatous change of the optic disc head, and also no glaucomatous visual field defect on standard automated perimetry. Red-free fundus photography and swept-source optical coherence tomography showed an ERM and wedge-shaped RNFL defect starting from the PIRD, not the optic disc head. He was diagnosed with non-glaucomatous RNFL defect in the right eye and was told to stop using topical hypotensive medication for the right eye. After 2 years of discontinuing the medication, the IOP was within the normal range, the RNFL defect showed no progression, and the visual field remained stationary.CONCLUSIONS: A non-glaucomatous RNFL defect can develop in association with PIRD in patients with idiopathic ERM. Examinations for PIRD as well as evaluation of the optic disc head are therefore necessary in patients with ERM and RNFL defect.
Aged ; Epiretinal Membrane ; Glaucoma ; Head ; Humans ; Intraocular Pressure ; Male ; Nerve Fibers ; Photography ; Reference Values ; Retinaldehyde ; Tomography, Optical Coherence ; Visual Field Tests ; Visual Fields

Since genetic models for retinal degeneration (RD) in animals larger than rodents have not been firmly established to date, we sought in the present study to develop a new rabbit model of drug-induced RD. First, intravitreal injection of N-methyl-N-nitrosourea (MNU) without vitrectomy in rabbits was performed with different doses. One month after injection, morphological changes in the retinas were identified with ultra-wide-field color fundus photography (FP) and fundus autofluorescence (AF) imaging as well as spectral-domain optical coherence tomography (OCT). Notably, the degree of RD was not consistently correlated with MNU dose. Then, to check the effects of vitrectomy on MNU-induced RD, the intravitreal injection of MNU after vitrectomy in rabbits was also performed with different doses. In OCT, while there were no significant changes in the retinas for injections up to 0.1 mg (i.e., sham, 0.05 mg, and 0.1 mg), outer retinal atrophy and retinal atrophy of the whole layer were observed with MNU injections of 0.3 mg and 0.5 mg, respectively. With this outcome, 0.2 mg MNU was chosen to be injected into rabbit eyes (n=10) at two weeks after vitrectomy for further study. Six weeks after injection, morphological identification with FP, AF, OCT, and histology clearly showed localized outer RD - clearly bordered non-degenerated and degenerated outer retinal area - in all rabbits. We suggest our post-vitrectomy MNU-induced RD rabbit model could be used as an interim animal model for visual prosthetics before the transition to larger animal models.
Animals ; Atrophy ; Intravitreal Injections ; Methylnitrosourea ; Models, Animal ; Models, Genetic ; Photography ; Rabbits ; Retina ; Retinal Degeneration ; Retinaldehyde ; Rodentia ; Tomography, Optical Coherence ; Vitrectomy

PURPOSE: To investigate the clinical manifestations and properties of remnant particles in the subconjunctival space after high-frequency radio-wave electrosurgery for conjunctivochalasis. METHODS: We performed a retrospective, observational case series with in vitro experimental imaging in nine eyes from eight patients who presented with small dark-gray lesions during follow-up after high-frequency radio-wave electrosurgery for conjunctivochalasis. General examination including slit-lamp examination and visual acuity testing was performed preoperatively and postoperatively. During follow-up, we evaluated remnant particles and any other complications including granuloma or conjunctival injection with slit-lamp photography and anterior optical coherence tomography. Coagulation tips were investigated with scanning electron microscope and energy dispersive X-ray spectroscopy to analyze the insulating electrode and assess changes to tips after repeated use. RESULTS: None of the patients included in this study experienced any change in visual acuity or major complications postoperatively. Small dark-gray lesions (0.3 to 0.5 mm in size) were observed in the inferior bulbar sub-conjunctival space in the location where high-frequency radio-wave electrosurgery had been performed. Cirrus high-definition optical coherence tomography images revealed focal hyper-reflection with a posterior shadow, suggesting foreign particles. Scanning electron microscopy and energy dispersive X-ray spectroscopy imaging analysis revealed peaks of carbon and fluorine complexes, consistent with the polytetrafluoroethylene coating on the electrode. CONCLUSIONS: There were no instances of inflammatory reaction, particle migration, or major complications due to particles. Physicians should be aware of the possibility of remnant polytetrafluoroethylene particles in subconjunctival tissue when using insulated coagulation tips subjected to repeat sterilization.
Carbon ; Electrodes ; Electrosurgery ; Fluorine ; Follow-Up Studies ; Granuloma ; Humans ; In Vitro Techniques ; Microscopy, Electron, Scanning ; Photography ; Polytetrafluoroethylene ; Retrospective Studies ; Spectrometry, X-Ray Emission ; Sterilization ; Tomography, Optical Coherence ; Visual Acuity

PURPOSE: We report a case of fundus albipunctatus discovered in a young patient. CASE SUMMARY: A 7.6-year-old female showed numerous small whitish-yellow flecks in the perimacular area and retinal periphery. Dark adapted 0.01 electroretinography (ERG) and dark adapted 3.0 ERG were profoundly reduced. At 26 months after the first visit, the best-corrected visual acuities were 1.0 right eye and 0.9 left eye. There were no pigmented lesions, atrophic lesions, or vascular abnormalities in the retina. Humphrey and Goldmann visual field tests were performed, but neither of the tests revealed any scotomas or other visual field defect. The number and size of characteristic numerous small whitish-yellow retinal flecks seemed almost unchanged. In spectral domain-optical coherence tomography (SD-OCT), the subretinal hyper-reflective lesions spanned the retinal pigment epithelium and the external limiting membrane. ERG showed improved dark adapted responses (dark adapted 0.01 ERG and dark adapted 3.0 ERG) after prolonged dark adaptation (2.5 hours). No family member showed any abnormal findings. CONCLUSIONS: Fundus albipunctatus is a rare disease in Koreans. We report a case diagnosed using fundus photography, SD-OCT, visual field tests, and ERG after prolonged dark adaptation (2.5 hours).
Child ; Dark Adaptation ; Electroretinography ; Female ; Humans ; Membranes ; Photography ; Rare Diseases ; Retina ; Retinal Pigment Epithelium ; Retinaldehyde ; Scotoma ; Tomography, Optical Coherence ; Visual Acuity ; Visual Field Tests ; Visual Fields

PURPOSE: To evaluate the effects of surgery depending on the follow-up duration after superior oblique tuck was performed as the first surgery in unilateral superior oblique palsy patients. METHODS: Sixteen patients who were followed-up for a minimum of 3 months were retrospectively evaluated. The vertical deviation, abnormal head posture, superior oblique underaction, and inferior oblique overaction were evaluated before and at 3, 6, and 12 months after the surgery and at the last follow-up. The angle between the center of the optic disc and fovea (disc-fovea angle) was measured using fundus photography to investigate changes in ocular torsion. RESULTS: The mean follow-up period was 24.9 ± 21.9 months and the mean tuck was 11.4 ± 4.0 mm. Vertical deviation <7 prism diopters in the primary position was observed in 53.9% of patients at 3 months postoperatively, 50.0% at 6 months, 83.3% at 12 months, and 62.5% at the last follow-up (p = 0.55). Head posture was improved in 66.7% of patients at 3 months, 71.4% at 6 months, 50% at 12 months, and 80% at the last follow-up after surgery (p = 0.73). Ocular torsion was decreased in 37.5% of patients at 3 months postoperatively, 66.7% at 6 months, 75% at 12 months, and 80.0% at the last follow-up (p = 0.11). Superior oblique underaction was improved in 100%, 77.8%, 60%, and 75% of the patients and inferior oblique overaction was improved in 100%, 88.9%, 85.7%, and 81.3% of the patients at postoperative month 3, 6, and 12, and at the last follow-up, respectively. CONCLUSIONS: Superior oblique tuck resulted in the maintenance of an improved condition of patients at 3, 6, and 12 months postoperatively, and there was no significant difference in motor measurements between the follow-up periods.
Follow-Up Studies ; Head ; Humans ; Paralysis ; Photography ; Posture ; Retrospective Studies

PURPOSE: To clarify the relationship between various factors (sociodemographic factors, health behavioral risk factors and health status, and diabetic factors) related to diabetic retinopathy and to suggest improvements regarding the associated medical examination. METHODS: The subjects were 1,444 diabetic patients diagnosed in the 5th Korean National Health and Nutrition Examination Survey (KNHANES), aged 19 years or older, who underwent non-mydriatic fundus photography. The criteria for diagnosing diabetes were a fasting glucose level ≥ 126 mg/dL and a previous diagnosis of diabetes or currently undergoing treatment. The diagnosis of diabetic retinopathy followed the modified Airlie House classification. Univariate and multivariate analyses of diabetic retinopathy were performed. RESULTS: Among the 1,444 patients who were diagnosed with diabetes, 277 had diabetic retinopathy; the prevalence rate was 19.18%. The higher the body mass index, the lower the risk of diabetic retinopathy by 0.924 times (p = 0.001; 95% confidence interval [CI], 0.883–0.966). The longer the duration of diabetes, the greater the risk of diabetic retinopathy; the prevalence period group of more than 11 years had a 26.025-fold higher risk than the newly diagnosed group (p < 0.001; 95% CI, 10.840–62.482). The risk of diabetic retinopathy increased with the hemoglobin A1c (HbA1c) level; the risk was 5.973-fold higher in the group with HbA1c above 11.0% (p < 0.001; 95% CI, 2.984–11.956) compared with the group with HbA1c < 6.0%. The risk of diabetic retinopathy was 2.050-fold greater with insulin injections (p = 0.003; 95% CI, 1.284–3.275). CONCLUSIONS: The risk of diabetic retinopathy was higher in patients with a longer duration of diabetes, a high HbA1c level, and in those using insulin. These findings highlight the need for early education and ophthalmologic examinations for at-risk patients.
Body Mass Index ; Classification ; Diabetic Retinopathy ; Diagnosis ; Education ; Fasting ; Glucose ; Health Behavior ; Humans ; Insulin ; Multivariate Analysis ; Nutrition Surveys ; Photography ; Prevalence ; Risk Factors

The human quest to master the anatomy and physiology of living systems started as early as 1600 BC, with documents from the Greeks, Indians, and Romans presenting the earliest systematic studies and advances. Following the fall of the Roman Empire, the progress slowed until the Renaissance renewed scientific interest in anatomy and physiology, ushering in an era of spectacular advances. Alongside the discoveries of modern science, innovations in media such as printing, photography and color reproduction, improved the accuracy of communicating science. Techniques for noninvasively viewing the human body, such as magnetic resonance imaging, opened up new ways of exploring and understanding anatomy, physiology, and disease pathogenesis. Advances in three-dimensional (3D)-technologies, including computer graphics and animation are directly linked to many advances in medicine and surgery. Anatomy education has come a long way from papyrus leaf inscriptions to computerized 3D modeling, holographic representation, and virtual reality-based software. The future presents unlimited options for studying and understanding anatomy as Google glasses, bioprinting, virtual reality, and allied technologies transform the world into a classroom. This review summarizes the journey of mankind to master anatomy and physiology.
Bioprinting ; Computer Graphics ; Education ; Eyeglasses ; Glass ; Human Body ; Humans ; Magnetic Resonance Imaging ; Photography ; Physiology ; Reproduction ; Roman World