Minimal Training Research Articles

Robust function guided color encoded single fringe pattern and unwrapping method

Fringe Projection Profilometry (Fringe Projection Profilometry，FPP), renowned for its speed, precision, and automation advantages, has found extensive applications in industries such as mechanical processing and quality inspection. A critical challenge within fringe projection techniques involves ensuring robust unwrapping while minimizing the necessary fringe images. While various unwrapping methods exist to reduce the number of projected images, there is a deficiency in efficient unwrapping methods developed under the guidance of error analysis theory. In this study, we derive a robustness function from FPP's error theory to assess the unwrapping robustness of different encoded images. Using this robustness function, we select highly robust single-color encoded fringe images and achieve unwrapping robustness with minimal training cost based on a single fringe pattern. Furthermore, this unwrapping process does not necessitate the establishment of complex training databases, as the K-nearest neighbor (K-Nearest Neighbor，KNN) algorithm learns the correspondence between image tricolor grayscale values and fringe orders from multi-frequency unwrapping method. Finally, experimental validation through a checkerboard measurement confirms that the proposed method can achieve robust unwrapping with low training costs using only one encoded fringe, thereby affirming the effectiveness of the introduced robustness function and the feasibility of the designed color encoded single fringe pattern unwrapping method.

Integralidade na formação de Terapeutas Ocupacionais: análise das percepções e estrutura curricular da Graduação

Introduction: Integrative and Complementary Health Practices (PICS) in the area of ​​Occupational Therapy (OT) require training and discussion in the graduation process to guarantee access and care within the integral reasoning of the body, mind, emotions and connections. Objectives: To verify the training, perceptions and experiences with PICS of OT undergraduates at the Faculty of Medicine of Ribeirão Preto at the University of São Paulo. Methods: Cross-sectional, exploratory, descriptive and quantitative study using an online questionnaire developed in research with undergraduates in the last semester and analysis of the curricular structure and teaching plans. Results and discussion: Of the total of 17 undergraduates, 12 reported knowledge about PICS (100%), 92% used them for personal purposes, and 17% stated doubts about their effectiveness and uncertainty about their credibility in the Brazilian Unified Health System (SUS) as a therapeutic resource in the profession. There was minimal training offered on PICS, of the 69 subjects in the undergraduate course, 3 dealt with the topic in a theoretical and experimental way, with a low workload and insufficient content for logic and professional use. Final considerations: There is a need for curricular changes to incorporate these practices as a therapeutic resource within the profession in order to guarantee access and quality care to the population.

Correlates of Professional Breastfeeding Perceived Role, Perceived Influence, and Confidence in Providing Lactation Support Among Registered Dietitians and Registered Nurses

Lactation support from health professionals is a crucial social determinant of health. Registered dietitians (RDs) and registered nurses (RNs) can play an important role in supporting breastfeeding, yet most have minimal formal lactation education and training. This study seeks to explore the correlates of professional breastfeeding perceived role, perceived influence, and confidence in providing lactation support among RDs and RNs. Using a cross-sectional design, a convenience sample of 111 credentialed providers completed an online survey assessing their breastfeeding-related training, experiences, knowledge, attitudes, and practices. We also examined perceptions of social support, intentions for future breastfeeding, professional roles, and confidence in lactation support. We tested for relationships between variables using chi-square, Fisher’s exact, and Mann–Whitney U tests and identified which correlates were associated with the dependent variables using bivariate logistic regression. Respondents who were breastfed as infants were 3.4 times more likely to agree that it is their responsibility to highlight health problems associated with infant formula when giving breastfeeding advice (p = 0.009). Those agreeing that people around them support breastfeeding were 8.0 times more likely to believe they can influence a woman’s breastfeeding decision and duration (p = 0.05). Respondents working in maternal/child/family health were 14.3 times more likely to feel confident in their ability to provide lactation counseling, guidance, and recommendations (p = 0.03). Educational institutions and employers should provide all RDs and RNs with opportunities for personal reflection and lactation training while strengthening breastfeeding social norms.

Automated analysis of flow cytometry data with minimal training files: Research evaluation of an elastic image registration algorithm for TBNK, stem cell enumeration, and lymphoid screening tube assays.

Automated analysis of flow cytometry data can improve objectivity and reduce analysis time but has generally required work by software and algorithm experts. Here, we investigated the performance of BD ElastiGate™ Software (hereafter ElastiGate), which allows users to automate gating by selecting gated training files, then uses elastic image registration to gate new files. Three assays of increasing complexity were examined: TBNK, stem cell enumeration (SCE), and lymphoid screening tube (LST). For TBNK analysis, 60 peripheral blood (PB) samples from normal, HIV+, and controls were tested with ground truth analysis by an existing automated method. For SCE, 128 samples including bone marrow (BM), cord blood (CB), and apheresis were tested with analysis by multiple manual analysts. For LST, 80 PB and 28 BM samples were tested with manual analysis. For ElastiGate, a minimal number of training files was selected. Results were compared by Bland-Altman or F1 score analysis. For TBNK, ElastiGate using three training files (1 control, 1 normal, 1 HIV+) showed mean %bias across all reported populations between -1.48% and 7.13% (average 2.08%). For SCE, ElastiGate using three BM and two CB training files showed median F1 scores >0.93 in comparison to >0.94 and >0.92 for two other manual analysts. For LST, ElastiGate using four training files for each of PB and BM showed median F1 scores >0.945 for 13 of 14 PB populations and 10 of 14 BM populations, with generally similar or better performance for normal samples compared to abnormal; populations with lower scores were often associated with lower agreement between manual analysts. Based on analysis of three assays with four sample types of increasing complexity, ElastiGate with minimal training files may perform as an automated gating assistant. The results reported here are for research use only, not for use in diagnostic or therapeutic procedures.

Towards a general computed tomography image segmentation model for anatomical structures and lesions

Numerous deep-learning models have been developed using task-specific data, but they ignore the inherent connections among different tasks. By jointly learning a wide range of segmentation tasks, we prove that a general medical image segmentation model can improve segmentation performance for computerized tomography (CT) volumes. The proposed general CT image segmentation (gCIS) model utilizes a common transformer-based encoder for all tasks and incorporates automatic pathway modules for task prompt-based decoding. It is trained on one of the largest datasets, comprising 36,419 CT scans and 83 tasks. gCIS can automatically perform various segmentation tasks using automatic pathway modules of decoding networks through text prompt inputs, achieving an average Dice coefficient of 82.84%. Furthermore, the proposed automatic pathway routing mechanism allows for parameter pruning of the network during deployment, and gCIS can also be quickly adapted to unseen tasks with minimal training samples while maintaining great performance.

A Robust Controller Based on Extension Sliding Mode Theory for Brushless DC Motor Drives

This paper presents the design of a robust speed controller for brushless DC motors (BLDCMs) under field-oriented control (FOC). The proposed robust controller integrates extension theory (ET) and sliding mode theory (SMT) to achieve robustness. First, the speed difference between the speed command and the actual speed of the BLDCM, along with the rate of change of the speed difference, are divided into 20 interval categories. Then, the feedback speed difference and the rate of change of the speed difference are calculated for their extension correlation with each of the 20 interval categories. The interval category with the highest correlation is used to determine the appropriate control gain for the sliding mode speed controller. This gain adjustment tunes the parameters of the sliding surface in the SMT, thereby suppressing the overshoot of the motor’s speed. Because a sliding surface reaching law of the sliding mode controller (SMC) adopts the exponential approach law (EAL), the system’s speed response can quickly follow the speed command in any state and exhibit an excellent load regulation response. The simplicity of this robust control method, which requires minimal training data, facilitates its easy implementation. Finally, the speed control of the BLDCM is simulated using Matlab/Simulink software (2023b version), and the results are compared with those of the SMC using the constant-speed approach law (CSAL). The simulation and experimental results demonstrate that the proposed robust controller exhibits superior speed command tracking and load regulation responses compared to the traditional SMC.

Novel Method of Measuring Pelvic Floor Muscle Motion May Improve Accessibility of Pelvic Floor Muscle Coordination Training.

Pelvic floor muscle ultrasound is an important clinical tool for improving motor coordination and even strength. Although the gold standard approach involves transperineal probe placement, this is not always feasible with sensitive populations, requires privacy owing to probe placement, and additional sonography training. This article introduces a novel transabdominal method for measuring pelvic floor muscle motion that incorporates a reference point within the bladder. The hypothesis is that the novel measurement will correlate positively with transperineal measurements. A total of 55 women (15 nulliparous, 40 parous; 20 continent, 35 incontinent) performed pelvic floor muscle contraction and strain. Transabdominal ultrasound measured bladder diagonal length (BDL) and transperineal ultrasound measured bladder neck height (BNH), levator plate length (LPL), and levator plate angle (LPA). Spearman's test measured the correlation between the measurement outcomes and an independent t test compared outcomes based on parity and stress urinary incontinence symptom status. Spearman's correlation showed moderate positive correlations between the pelvic floor measurements for both tasks, which reduced slightly when grouping by parity and symptom status. Group differences were significant for BDL during the muscle contraction, factoring in SUI symptoms (p = 0.019) and parity status (p = 0.005) and LPL during contraction, factoring in parity status (p = 0.033). BDL correlates with BNH, LPL, and LPA with slightly reduced correlation when factoring in parity and continence status. The advantages of the method include accessibility for sensitive populations, nontraditional positions due to the anatomical reference point, functional locations due to limited privacy needs, and minimal training required for pelvic floor therapists to incorporate into rehabilitation.

EMS Clinicians in the West Texas Area Frequently Encounter Firearms During Patient Assessments with Limited Gun Safety Training

Introduction - Firearms are commonly encountered in the prehospital setting, sometimes with devastating consequences. However, the frequency with which EMS workers find and handle firearms when evaluating patients in the field and the firearm safety training they have received remains largely unstudied. Objectives - We sought to answer the following questions: 1) How frequently do EMS personnel in West Texas and Southern New Mexico USA encounter and handle firearms when caring for patients? 2) How many of these clinicians are aware of agency policy or have received agency training in the safe handling of firearms? 3) Do these clinicians support integrating firearm training into the EMS curriculum? Methods - In this observational, cross-sectional study, a survey evaluating weapon and firearm encounters, confidence handling firearms, and formal firearms training was distributed to EMS providers in West Texas and Southern New Mexico between July 1, 2022, and January 1, 2023. Results - Two hundred forty-seven out of a potential 609 EMS clinicians completed the online survey, representing a 41% response rate. Among respondents, 61% reported encountering firearms at least once per year. These firearms were handled by EMS personnel over a quarter of the time. Sixty-eight percent of prehospital providers were unaware of any agency policy regarding handling firearms. Despite broad personal experience with firearms, 90% of respondents received no agency training in gun safety. Eighty-seven percent of providers reported they would attend an agency training course on firearm safety, and 95% indicated that this topic should be added to the EMS curriculum. Conclusion - EMS personnel in West Texas and Southern New Mexico routinely encounter and handle guns despite minimal agency firearm safety training. This initial study may demonstrate a potential need for introducing firearm safety didactics and training into the EMS curriculum, and the need for additional research.

Training Needs for School Staff Supporting Students Returning to School After a Psychiatric Hospitalization

AbstractSupporting students returning to school after a mental health crisis often involves more training than many school staff members receive. With the increase in youth mental health diagnoses, there has also been an increase in the number of youth requiring psychiatric emergency department visits and hospitalizations. As such, this study employed a basic qualitative design to gather the perspectives of school staff who support students’ mental health about their experiences and training needs related to supporting youth returning to school after psychiatric hospitalization. Semi-structured interviews were conducted with 10 school mental health professionals or administrators. Thematic analysis was used to analyze the data. Three themes were identified: (1) most participants received minimal formal training in graduate school on hospital-to-school transition, (2) most participants learned about hospital-to-school transition on the job, and (3) participants made recommendations and identified specific training needs. Implications for training are discussed including a need for variety (e.g., some practitioners need basic training while others need more advanced training) and different format preferences (in-person may be preferred but online asynchronous is more convenient).

Deep learning network for indoor point cloud semantic segmentation with transferability

Semantic segmentation is crucial for interpreting point cloud data and plays a fundamental role in automating the creation of as-built BIM. Existing neural network models for semantic segmentation often heavily rely on the training dataset, resulting in a significant performance drop when applied to new datasets. This paper presents AttTransNet, a neural network model for automated point cloud semantic segmentation. Its attention-based pooling module improves local feature extraction from point clouds while reducing computational costs. The transfer learning framework enhances segmentation accuracy with minimal training on target datasets. Comparative experiments show that AttTransNet reduces training time by 80 % and improves segmentation accuracy by over 20 % compared with other SOTA methods. Cross-dataset experiments reveal that the transfer learning framework increases accuracy on new datasets by 150 %. By adding semantic information to point clouds, AttTransNet aids BIM modelers with direct reference, encouraging broader application of automated point cloud segmentation in the industry.

Caregiver Wellness after Traumatic Brain Injury (CG-Well): Protocol for a randomized clinical trial

IntroductionAfter injury, survivors of moderate to severe traumatic brain injury (msTBI) depend on informal family caregivers. Upwards of 77% of family caregivers experience poor outcomes, such as adverse life changes, poor health-related quality of life, and increased depressive symptoms. Caregivers frequently report minimal support or training to prepare them for their new role. The majority of previously developed caregiver and caregiver/survivor dyad interventions after msTBI focus on providing information to either survivors only, or to long-term caregivers, rather than to the new caregiver. This manuscript describes the protocol of an ongoing randomized control trial, Caregiver Wellness after TBI (CG-Well), developed to provide education, support, and skill-building to caregivers of adults with msTBI, beginning when the survivor is early in the clinical course. MethodsWithin two weeks of admission to the ICU, participants are randomized to CG-Well online modules (intervention group, n = 50 dyads) or information, support, and referral (ISR) e-bulletins that exist in the public domain (control group, n = 50 dyads) over the first six months after their family member’s msTBI. Both groups receive regular phone calls. The primary outcome is intervention satisfaction at six months. ResultsEnrollment began in March, 2022 and is projected to complete October 2024. We have enrolled approximately 70% of participants at this time. Primary analysis completion is anticipated April, 2025. DiscussionThis RCT is designed to evaluate caregiver satisfaction by addressing the need for tailored supportive care for caregivers of msTBI beginning during the ICU admission. Trial RegistrationClinicaltrials.gov Registration Number: NCT05307640

The Impact of Diagnosis-Specific Plan Templates on Admission Note Writing Time: A Quality Improvement Initiative.

Background There are limited objective studies regarding the effectiveness of strategies to alleviate the documentation burden on resident physicians. Objective To develop and implement diagnosis-specific templates for the plan of care section of inpatient admission notes, aiming to reduce documentation time. Methods Twelve templates for the plan of care section of admission notes were written by the study authors, reviewed by attending physicians, and shared with the residents through the electronic health record (EHR) on September 23, 2022. EHR audit log data were collected to examine admission note writing times, supplemented by resident feedback on acceptability via an anonymous survey. Feasibility measures included time investment, experience with the EHR, and resident training. Results Between July 1, 2021 and June 30, 2023, 62 pediatric residents contributed 9840 admission notes. The templates were used in 557 admission notes. The mean total time spent on an admission note decreased from 97.9 minutes pre-intervention to 71.0 minutes post-intervention with the use of a template; an adjusted reduction of 23% (95% CI 16%-30%; P<.001). The mean attending time spent editing an admission note was unchanged. The survey results underscored wide acceptability of the templates among the residents. Feasibility data showed that the project required minimal time investment from the health care informatics team and minimal resident training. Conclusions Using templates in the care plan section of admission notes reduces the time residents spend writing admission notes.

A Minimal Training Protocol Improves Strength And Aerobic Fitness In Trained And Untrained Populations

A Minimal Training Protocol Improves Strength And Aerobic Fitness In Trained And Untrained Populations

Adaptive Neuro-Fuzzy Interference System (ANFIS) Control of a Dynamic, Two-Region Nuclear Power Plant Pressurizer Model

Abstract Designing modern control systems is a critical factor in producing rigid control and effective performance of non-linear and complex systems—particularly employing intelligence-based controllers, derived from soft computing algorithms. It is known to be well capable of exploiting tolerances for uncertainty and nonlinearity. Fuzzy logic, which utilizes soft computing techniques, deals with vague information and approximate reasoning, yet it lacks effective learning capability, while ANN is known for exceptional learning and adaptation of training data. Adaptive neuro-fuzzy interference system (ANFIS), a hybrid of these two algorithms, is a fuzzy interference system optimized by neural networks. Most nuclear generating stations still use PID controllers, which does not show good controlling capabilities, resulting in large coolant level overshoot and longer settling time. This paper bridges this gap by testing an ANFIS approach that yields high predictive and control capability. In validating the configured control loop model, three loss-of-load transients from a Shippingport reactor were tested, trained and demonstrated using the simulations in the MATLAB/Simulink environment. The minimal training RMSE for the 51 MW(e), 74 MW(e), and 105 MW(e) loss-of-load transients are 18.85%, 19.37%, and 24.36%. The pressure response showed ideal output, with all three steady-state pressures close at setpoint (14 MPa), proving that the ANFIS controller is well capable of rejecting disturbances with lesser overshoot and faster settling times in maintaining level setpoint. Validating solely the pressurizer model was executed in a turbine leading power trip from a 100% to 75% reduction range in PCTRAN, a pressurized water reactor (PWR) simulator made available by IAEA. The comparative performance exhibited a good fit between the reported simulation data and model data. Both results against simulation and experimental transients captured the effective predictive and control capabilities of the pressurizer unit and control system.

Self-supervised learning-based re-parameterization instance segmentation for hazardous object in terahertz image

Recently, terahertz imaging technology has shown widespread potential applications in the public security screening field. Previous terahertz hazardous object detection techniques primarily relied on manual recognition and image processing methods. Some solutions incorporating deep learning technologies depend on large quantities of high-quality data, making it challenging to achieve low-cost and high-performance detection. To solve the issue of dependency on large amounts of high-quality data, we propose a diversified dynamic structure You Only Look Once (DDS-YOLO) model based on masked image modeling and structural reparameterization for the instance segmentation of hazardous objects in terahertz security inspection images. To address the scarcity and annotating difficulty problems of terahertz security inspection image samples, we combine automatic data strategies with masked image modeling for self-supervised learning. We propose a multilevel feature refinement fusion mechanism to enhance the quality of learned feature representations. The backbone parameter transfer and fine-tuning training strategies are employed to achieve hazardous object instance segmentation on the terahertz dataset. To address the low detection accuracy issue caused by the poor terahertz image quality, we develop a reparameterizable hierarchical structure for the backbone, improve a multi-scale feature-integrating neck, and design a dynamically decoupled head with lower computational requirements to enhance the performance of the instance segmentation model. Experimental results demonstrate that the proposed model accurately outputs detection boxes, categories, and segmentation masks for hazardous objects with minimal training samples. The comparative experimental results indicate that the proposed model outperforms existing state-of-the-art methods in terms of detection performance. The proposed DDS-YOLO model achieves 59.3 % in mask mean Average Precision (mAP) and 61.3 % in box mAP, and the model parameters and computational requirements also meet practical application scenarios.

An Outline of Integrating Vision Screening at a Student-Run Free Health Clinic

Visual impairment (VI) is a pervasive issue associated with a significant financial burden, diminished health outcomes, and an overall reduced quality of life. This condition disproportionately affects uninsured patients as they face limited access to affordable care. For this reason, FaithCare Clinic, a free, student-run clinic in Augusta, Georgia that serves uninsured and underinsured patients at least two standard deviations below the poverty line, implemented a vision screening and referral protocol to better serve its patients. Patients were approached after check-in for their appointment, but prior to seeing the physician, and were screened with a Snellen Eye Chart and Amsler Grid to assess for refractive error and other types of VI. If they screened positive, they were referred to low cost, local resources for further care. Data was collected over a period of 17 months with 47.8% of the patients seen in clinic offered vision screening. Of the patients offered screening, the majority accepted (79.1%). Half of patients screened were cleared while the other half were referred for further care. These results illustrate that patients of a free clinic are willing to undergo vision screening and can benefit from its offering due to the high rates of VI in this population. Visual disabilities are a heavy burden, especially on the uninsured and underinsured populations. Implementing vision screening in free clinics across the country can identify and facilitate additional care in an at-risk population with minimal training and few additional resources.

Parents caring and sham-feeding their child born with Esophageal atresia at home while waiting for reconstructive surgery.

For children with Esophageal atresia who have to wait for reconstructive surgery, long hospital stay, delayed introduction of oral feeds and hampered oro-motor function has traditionally been draw-backs for this treatment as the patients have minimal training of oro-motor function while waiting for surgery. In this paper, we present the concept of sham-feed at home awaiting reconstructive surgery with the aim to obliviate these problems. The aim was to describe the characteristics of patients with Esophageal atresia waiting for reconstructive surgery sham-feeding at home by their parents and further describe adverse events that arose. The study is a retrospective descriptive single center study on all children with a delayed reconstruction of Esophageal atresia who was sham-fed by their parents at home before reconstructive surgery between January 2010 and January 2023 at the Karolinska University Hospital, Stockholm. Nine patients where home waiting for reconstructive surgery for a median of 72days. No adverse events were reported related to the sham-feed procedure at home. The children had reconstructive surgery at a median 120days of age. Five of the children ate full meals orally day 8-27 after surgery. Two children ate fully before 1year after surgery. Two children had surgery less than 1year ago and were not eating fully orally at the time of data collection. Sham-feeding at home by the parents was safe and feasible with the benefits of a prolonged time out of hospital awaiting reconstructive surgery.

Diagnosis of suspected pediatric distal forearm fractures with point-of-care-ultrasound (POCUS) by pediatric orthopedic surgeons after minimal training

BackgroundSeveral studies have advocated the use of ultrasound to diagnose distal forearm fractures in children. However, there is limited data on the diagnostic accuracy of ultrasound for distal forearm fractures when conducted by pediatric surgeons or trainees who manage orthopedic injuries in children. The objective of this study was to determine the diagnostic accuracy of point-of-care ultrasound (POCUS) for pediatric distal forearm fractures when conducted by pediatric surgeons and trainees after minimal training.MethodsThis diagnostic study was conducted in a tertiary hospital emergency department in Germany. Participants were children and adolescents under 15 years of age who presented to the emergency department with an acute, suspected, isolated distal forearm fracture requiring imaging. Pediatric surgeons and trainees, after minimal training for sonographic fracture diagnosis, performed 6-view distal forearm POCUS on each participant prior to X-ray imaging. All data was retrospectively collected from the hospital’s routine digital patient files. The primary outcome was the diagnostic accuracy of POCUS compared to X-ray as the reference standard.ResultsFrom February to June 2021, 146 children under 15 met all inclusion and exclusion criteria, and 106 data sets were available for analysis. Regarding the presence of a fracture, X-ray and Wrist-POCUS showed the same result in 99.1%, with 83/106 (78.3%) fractures detected in both modalities and one suspected buckle fracture on POCUS not confirmed in the radiographs. Wrist-POCUS had a sensitivity of 100% (95% CI [0.956, 1]) and a specificity of 95.8% (95% CI [0.789, 0.999]) compared to radiographs. In 6 cases, there were minor differences regarding a concomitant ulnar buckle. The amount of prior ultrasound training had no influence on the accuracy of Wrist-POCUS for diagnosing distal forearm fractures. All fractures were reliably diagnosed even when captured POCUS images did not meet all quality criteria.ConclusionPediatric surgeons and trainees, after minimal training in POCUS, had excellent diagnostic accuracy for distal forearm fractures in children and adolescents using POCUS compared to X-ray.

Sosialisasi Kepemimpinan Bagi Pengurus OSIS SMP : Membangun Pemimpin Masa Depan Yang Berkarakter dan Inovatif

The Intra-School Student Organization (OSIS) at the junior high school level plays a crucial role in developing students' leadership skills. However, a lack of understanding of leadership concepts and minimal practical training are major obstacles to developing this potential. This research aims to enhance the leadership competencies of OSIS board members at SMP Negeri 1 Sumberrejo through a leadership socialization and training program. The implementation method used involves socialization and interactive discussions with all OSIS board members as participants. The results of the activities show that the socialization successfully increased participants' understanding of leadership concepts, ethics, responsibilities, and basic leadership skills such as effective communication, decision-making, and teamwork. The interactive Q&amp;A sessions and distribution of door prizes also played a role in increasing participants' engagement and motivation. It is hoped that this activity will foster the development of strong, innovative leaders who are ready to face future challenges.

DAMM for the detection and tracking of multiple animals within complex social and environmental settings

Accurate detection and tracking of animals across diverse environments are crucial for studying brain and behavior. Recently, computer vision techniques have become essential for high-throughput behavioral studies; however, localizing animals in complex conditions remains challenging due to intra-class visual variability and environmental diversity. These challenges hinder studies in naturalistic settings, such as when animals are partially concealed within nests. Moreover, current tools are laborious and time-consuming, requiring extensive, setup-specific annotation and training procedures. To address these challenges, we introduce the 'Detect-Any-Mouse-Model' (DAMM), an object detector for localizing mice in complex environments with minimal training. Our approach involved collecting and annotating a diverse dataset of single- and multi-housed mice in complex setups. We trained a Mask R-CNN, a popular object detector in animal studies, to perform instance segmentation and validated DAMM’s performance on a collection of downstream datasets using zero-shot and few-shot inference. DAMM excels in zero-shot inference, detecting mice and even rats, in entirely unseen scenarios and further improves with minimal training. Using the SORT algorithm, we demonstrate robust tracking, competitive with keypoint-estimation-based methods. Notably, to advance and simplify behavioral studies, we release our code, model weights, and data, along with a user-friendly Python API and a Google Colab implementation.