5 results about "Pap smears" patented technology

Disclosed herein is a method for training a network to detect and classify abnormal pathologies in images if cells. Specifically, the network uses a deep framework optimally trained to detect and classify abnormal cervical cells in pap smear images.

The subject invention is related to the HVS and Pap smear testing apparatus providing Pap smear testing for Human Papilloma Virus (HPV) and HSV test for culture and sensitivity by doctor and patient automatically and being characterized by outer cylinder (1), head (2), interior side (3), end side (4), ring 1 (5), spiral end (6), ring 2a (7), internal cylinder 1 (8), piston cover (9), cylinder (10), protective cover (11), end part (12), outer end side (13), interior end side (14), flexible tube (15), medical tube (16), spring 1 (17), recoil cylinder 1 (18), line 1 (19.a), line 2 (19.b), ring 3 (20), ring 2b (21), spring 2 (22), internal cylinder 2 (23), ring 4 (24), hole 1 (25), tip holder (26), spring 3 (27), recoil cylinder 2 (28), hole 2 (29), circle 1 (30), coil (31), ring 5 (32), ring 6 (33), head bar 1 (34), cotton (35), empty space (36), accuracy sign (37), cone (38), circle 2 (39), black rubber (40), rear part (41), small cylinder 1 (42), wing (43), small cone (44), small cylinder 2 (45), head bar 2 (46), brush (47), ring 7 (48), brush bristle (49), sharp edge (50), and hole 3 (51).

The invention provides an artificial-intelligence–based platform for automated analysis of Pap smear slides. The system integrates preprocessing, dual deep learning models (CNN-Transformer and EfficientNet-LSTM), and reporting modules to classify cytological images into diagnostic categories including NILM, ASC-US, LSIL, HSIL, and SCC. The platform includes interpretability outputs, secure data management, and active learning capabilities, enabling scalable, accurate, and transparent cervical-cancer screening across diverse laboratory settings. The platform is suitable for implementation in clinical pathology laboratories, telemedicine networks, and population-level screening programs. It allows rapid, reproducible, and objective evaluation of cytology slides, improving throughput while reducing reliance on manual slide examination. The invention is deployable on local servers, private clouds, or public cloud infrastructures and is adaptable to various cytology specimens. Adoption of this system enhances early detection of precancerous lesions, reduces inter-observer variability, and facilitates integration with laboratory information systems. It also supports continuous learning and adaptation to evolving imaging protocols. The invention provides multiple advantages over existing methods: (1) Dual-model architecture combining CNN-Transformer and EfficientNet- LSTM ensures robust classification across both dense and sparse cellular regions. (2)Preprocessing and adaptive tiling improve feature extraction from variable-quality images. (3)Interpretability modules enhance clinician trust and facilitate regulatory compliance. (4) Active learning allows continuous improvement based on expert feedback. (5) Modular deployment supports both local laboratory and cloud-based operation. (6) Data security features meet international standards for privacy and encryption. (7) High scalability enables screening of large slide volumes without compromising accuracy. The invention provides a clinically relevant, efficient, and technologically advanced solution for automated cervical-cancer screening, applicable in diverse healthcare environments and adaptable to future cytology domains.

We disclose an apparatus for vaginal cell collection which can reliably collect a suitable specimen for cytopathological, molecular and other examination or analysis but which does not have the discomfort of a conventional pap smear test. The device comprises an insertion member having a distal, insertion end, a proximal end and a closable interior cavity; a flexible membrane having an outer, cell sampling surface and an inner surface, wherein said membrane is sealingly attached to the distal, insertion end of said insertion member and held within the interior cavity; such that, in use, pressurisation of the interior cavity to at least a first elevated pressure causes the membrane to emit from the distal end of said insertion member to make contact with the vaginal mucosal surface and pressurisation of the interior cavity to a second reduced pressure causes the membrane to invert and return to the interior cavity of said insertion member; the insertion member having an exterior surface comprising an elongate tip portion with a smooth exterior surface which extends from the distal, insertion end at least as far back as a stop portion comprising at least one transversely-protruding lip extending outwardly from the smooth exterior surface of the tip portion thereby to inhibit insertion beyond the stop portion. The insertion member can comprise an inner section at least part of which is a hollow tubular section thus defining the interior cavity, and a separate outer sleeve attachable to the inner section to extend around the inner section rearwardly from the distal, insertion end, and which includes the at least one lip. The outer sleeve can also include the elongate tip portion with a smooth exterior, and can be attachable to the inner section via screw threads provided on an outer surface of the inner section and an inner surface of the outer sleeve.

A metaheuristically optimized deep learning system for the automated detection of cervical cancer based on Pap smear images, consisting of: an image acquisition module configured to receive Pap smear images; a preprocessing module designed for noise reduction, contrast enhancement, and edge detection; a deep learning-based feature extraction module that includes pre-trained convolutional neural networks; a feature optimization module that uses binary metaheuristic algorithms to select optimal feature subsets; and a classification module that includes a machine learning classifier configured to classify cervical cells into normal and abnormal classes.