HairNet2: deep learning to quantify cotton leaf hairiness, a complex genetic and environmental trait.

BACKGROUND: Cotton accounts for 80% of the global natural fibre production. Its leaf hairiness affects insect resistance, fibre yield, and economic value. However, this phenotype is still qualitatively assessed by visually attributing a Genotype Hairiness Score (GHS) to a leaf/plant, or by using the HairNet deep-learning model which also outputs a GHS. Here, we introduce HairNet2, a quantitative deep-learning model which detects leaf hairs (trichomes) from images and outputs a segmentation mask and a Leaf Trichome Score (LTS). RESULTS: Trichomes of 1250 images were annotated (AnnCoT) and a combination of six Feature Extractor modules and five Segmentation modules were tested alongside a range of loss functions and data augmentation techniques. HairNet2 was further validated on the dataset used to build HairNet (CotLeaf-1), a similar dataset collected in two subsequent seasons (CotLeaf-2), and a dataset collected on two genetically diverse populations (CotLeaf-X). The main findings of this study are that (1) leaf number, environment and image position did not significantly affect results, (2) although GHS and LTS mostly correlated for individual GHS classes, results at the genotype level revealed a strong LTS heterogeneity within a given GHS class, (3) LTS correlated strongly with expert scoring of individual images. CONCLUSIONS: HairNet2 is the first quantitative and scalable deep-learning model able to measure leaf hairiness. Results obtained with HairNet2 concur with the qualitative values used by breeders at both extremes of the scale (GHS 1-2, and 5-5+), but interestingly suggest a reordering of genotypes with intermediate values (GHS 3-4+). Finely ranking mild phenotypes is a difficult task for humans. In addition to providing assistance with this task, HairNet2 opens the door to selecting plants with specific leaf hairiness characteristics which may be associated with other beneficial traits to deliver better varieties.

Morphometrical and morphological study of mental foramen in dry dentulous mandibles of South Andhra population of India.

BACKGROUND: Mental foramen (MF) is an anatomical structure of particular importance in local anesthesia and surgical procedures in terms of achieving effective mandibular nerve blocks and avoiding injuries to the neurovascular bundles. AIM: To determine the morphometry and morphology of MF in south Andhra population of India, hitherto unreported. MATERIALS AND METHODS: Ninety dry dentulous mandibles of both sexes were examined for position, size, shape and number of MF. RESULTS: Various parameters investigated are, the horizontal distance between (1) symphysis menti and MF was 27.2 mm on right and 27.7 mm on the left, (2) MF and posterior border of ramus was 70.7 mm on both sides, vertical distance between (3) MF and inferior border of mandible was 16.5 mm on right and 14.3 mm on left, (4) alveolar crest and MF was 13.7 mm on right and 16.4 on left, (5) distance between the MF and below the apex of premolar socket was +2.8 mm on right and +3.5 mm on left and above the socket was -2.8 mm on right and -2.7 mm on left. Occurrence of MF below the second premolar tooth was found to be highest (73.2%). Average size of MF was larger on left and its way of exit was in postero-superior direction. Shape of MF was round in 79% and oval in 21% and double MF was found in 8.9% of mandibles. CONCLUSIONS: In the present study, most common position of MF was found below the apex of second premolar in 73.2% and between the second premolar and first molar in 19% of mandibles. The other morphometrical findings of this study may be implicated by dental practitioners and maxillofacial surgeons.

Variant Anatomy of the Celiac Trunk and its Branches / Variación Anatómica del Tronco Celíaco y sus Ramas

The knowledge of abdominal vascular anatomy is very important for surgeons and radiologists to perform many of the clinical diagnostic evaluations. The celiac trunk, one of the branches of the abdominal aorta shows numerous variations in its branching pattern and its branches. The present study is to demonstrate the rare branching pattern of celiac trunk, into hepatogastric and hepatosplenic trunks. The hepatogastric trunk divided into left gastric and accessory left hepatic arteries and the hepatosplenic into common hepatic and splenic artery. The inferior phrenic artery was arising from left gastric artery. The gastroduodenal artery divided into right gastroepiploic artery and a common trunk for right gastric and anterior superior pancreaticoduodenal artery. The posterior superior pancreatico-duodenal artery was arising directly from the gastroduodenal artery and supraduodenal from proper hepatic artery. The variant anatomy of the celiac trunk as found in the present case may be clinically significant during invasive procedures like angiography, chemotherapy, chemoembolization and other surgical conditions of the abdomen.

El conocimiento de la anatomía vascular abdominal es importante para los cirujanos y radiólogos para realizar las evaluaciones de diagnóstico clínico. El tronco celíaco, una de las ramas de la parte abdominal de la aorta presenta numerosas variaciones en su patrón de ramificación y sus ramas colaterales. El presente estudio muestra un raro patrón de ramificación del tronco celíaco, en los troncos hepatogástrico y hepatoesplénico. El tronco hepatogástrico se dividió en las arterias gástrica izquierda y accesoria hepática izquierda, mientras que el hepatoesplénico en las arterias hepática común y esplénica. La arteria frénica inferior se originó desde la arteria gástrica izquierda. La arteria gastroduodenal se dividió en la arteria gastroepiploica derecha y en un tronco común para las arterias gástrica y pancreaticoduodenal anterosuperior. La arteria pancreaticoduodenal posterosuperior se originó directamente de la arteria gastroduodenal y la arteria supraduodenal de la arteria hepática. La variaciónanatómica del tronco celíaco presente en este caso puede ser clínicamente significativa durante procedimientos invasivos como la angiografía, quimioterapia, quimioembolización y afecciones quirúrgicas del abdomen.