This paper presents an extensive exploration and comparative analysis of lightweight face recognition (FR) models, specifically focusing on MobileFaceNet and its modified variant, MMobileFaceNet. The need for efficient FR models on devices with limited computational resources has led to the development of models with reduced memory footprints and computational demands without sacrificing accuracy. Our research delves into the impact of dataset selection, model architecture, and optimization algorithms on the performance of FR models. We highlight our participation in the EFaR-2023 competition, where our models showcased exceptional performance, particularly in categories restricted by the number of parameters. By employing a subset of the Webface42M dataset and integrating sharpness-aware minimization (SAM) optimization, we achieved significant improvements in accuracy across various benchmarks, including those that test for cross-pose, cross-age, and cross-ethnicity performance. The results underscore the efficacy of our approach in crafting models that are not only computationally efficient but also maintain high accuracy in diverse conditions.

LEBANON, NH - Recently, deep learning methods have shown promising results for analyzing histological patterns in microscopy images. These approaches, however, require a laborious, high-cost, manual annotation process by pathologists called "region-of-interest annotations." A research team at Dartmouth and Dartmouth-Hitchcock Norris Cotton Cancer Center, led by Saeed Hassanpour, PhD, has addressed this shortcoming of current methods by developing a novel attention-based deep learning method that automatically learns clinically important regions on whole-slide images to classify them. The team tested their new approach for identifying cancerous and precancerous esophagus tissue on high-resolution microscopy images without training on region-of-interest annotations. "Our new approach outperformed the current state-of-the-art approach that requires these detailed annotations for its training," concludes Hassanpour.

Researchers have developed a deep learning model to accurately identify cancerous esophagus tissue on microscopy images instead of the high-cost, time-consuming manual annotation process used by pathologists. A research team at Dartmouth and Dartmouth-Hitchcock Norris Cotton Cancer Center tested their new machine learning approach for identifying cancerous and precancerous esophagus tissue on high-resolution microscopy images. Whole-slide images were collected from patients who underwent endoscopic esophagus and gastroesophageal junction mucosal biopsy, and an attention-based deep neural network framework was used to classify microscopy images. Results of the study were published on Wednesday in JAMA Network Open. "Previous methods for analyzing microscopy images were limited by bounding box annotations and unscalable heuristics," state the authors.

Atypical ductal hyperplasia (ADH) is a breast lesion associated with a four- to-five-fold increase in the risk of breast cancer. ADH is primarily found using mammography and identified on core needle biopsy. Despite multiple passes of the lesion during biopsy, only portions of the lesions are sampled. Other variable factors influence sampling and accuracy such that the presence of cancer may be underestimated by 10 to 45 percent. Currently, surgical removal is recommended for all ADH cases found on core needle biopsies to determine if the lesion is cancerous.

Researchers have developed a machine learning model that can classify different types of lung cancer in less than a minute. The model could be used to assist doctors in determining tumour patterns and subtypes, which is an important part of prognosis and so determining the appropriate treatment. The Dartmouth-Hitchcock Medical Center researchers say the machine learning model can perform on par with three practicing pathologists. Machine learning, a subset of AI, is a type of algorithm that trains itself to predict outcomes and learn from successes and failures. In this model, the researchers used unsupervised machine learning, which means the model automatically trawls through millions of training data to identify subtle correlations and so teach itself.

A Dartmouth research team is harnessing machine learning technology to predict malignant breast cancer lesions. Saeed Hassanpour, assistant professor of biomedical data science and epidemology at the Geisel School of Medicine, and his team are focused on developing this technology to predict the possibility that a breast lesion found during medical examinations is or will become cancerous. Hassanpour said that breast cancer screenings are widely used, but can induce a false positive, which put women in danger of overdiagnosis and overtreatment. He explained that typically, if a lesion is found after a mammography, doctors perform a core needle biopsy on the patient. If a marker for high risk breast cancer incidences, known as atypical ductal hyperplasia, is found, surgery is performed to determine whether the lesion is malignant or benign, according to Hassanpour.

LEBANON, NH - Atypical ductal hyperplasia (ADH) is a breast lesion associated with a four- to five-fold increase in the risk of breast cancer. ADH is primarily found using mammography and identified on core needle biopsy. Despite multiple passes of the lesion during biopsy, only portions of the lesions are sampled. Other variable factors influence sampling and accuracy such that the presence of cancer may be underestimated by 10-45%. Currently, surgical removal is recommended for all ADH cases found on core needle biopsies to determine if the lesion is cancerous.